SemaTyP: a knowledge graph based literature mining method for drug discovery

This study builds a coronavirus knowledge graph (KG) by merging two information sources. The first source is Analytical Graph (AG), which integrates more than 20 different public datasets related to drug discovery. The second source is CORD-19, a collection of published scientific articles related to COVID-19. We combined both chemo genomic entities in AG with entities extracted from CORD-19 to expand knowledge in the COVID-19 domain. Before populating KG with those entities, we perform entity disambiguation on CORD-19 collections using Wikidata. Our newly built KG contains at least 21,700 genes, 2500 diseases, 94,000 phenotypes, and other biological entities (e.g., compound, species, and cell lines). We define 27 relationship types and use them to label each edge in our KG. This research presents two cases to evaluate the KG’s usability: analyzing a subgraph (ego-centered network) from the angiotensin-converting enzyme (ACE) and revealing paths between biological entities (hydroxychloroquine and IL-6 receptor; chloroquine and STAT1). The ego-centered network captured information related to COVID-19. We also found significant COVID-19-related information in top-ranked paths with a depth of three based on our path evaluation.

Download Full-text

Literature mining method RaJoLink for uncovering relations between biomedical concepts

Journal of Biomedical Informatics ◽

10.1016/j.jbi.2008.08.004 ◽

2009 ◽

Vol 42 (2) ◽

pp. 219-227 ◽

Cited By ~ 41

Author(s):

Ingrid Petriĕ ◽

Tanja Urbanĕiĕ ◽

Bojan Cestnik ◽

Marta Macedoni-Lukšiĕ

Keyword(s):

Literature Mining ◽

Mining Method

Download Full-text

Developing a Deeper Understanding of Autism: Connecting Knowledge through Literature Mining

Autism Research and Treatment ◽

10.1155/2011/307152 ◽

2011 ◽

Vol 2011 ◽

pp. 1-8 ◽

Cited By ~ 4

Author(s):

Marta Macedoni-Lukšič ◽

Ingrid Petrič ◽

Bojan Cestnik ◽

Tanja Urbančič

Keyword(s):

Full Text ◽

Literature Mining ◽

Mining Method ◽

Abc Model ◽

Ontology Construction ◽

Pathological Conditions ◽

Nf Kappab ◽

Available Information ◽

Coherent Picture ◽

The Brain

In the field of autism, an enormous increase in available information makes it very difficult to connect fragments of knowledge into a more coherent picture. We present a literature mining method, RaJoLink, to search for matched themes in unrelated literature that may contribute to a better understanding of complex pathological conditions, such as autism. 214 full text articles on autism, published in PubMed, served as a source of data. Using ontology construction, we identified the main concepts of what is already known about autism. Then, the RaJoLink method, based on Swanson's ABC model, was used to reveal potentially interesting, but not yet investigated, connections between different concepts in research. Among the more interesting concepts identified with RaJoLink in our study were calcineurin and NF-kappaB. Both terms can be linked to neuro-immune abnormalities in the brain of patients with autism. Further research is needed to provide stronger evidence about calcineurin and NF-kappaB involvement in autism. However, the analysis presented confirms that this method could support experts on their way towards discovering hidden relationships and towards a better understanding of the disorder.

Download Full-text

Literature mining in support of drug discovery

Briefings in Bioinformatics ◽

10.1093/bib/bbn035 ◽

2008 ◽

Vol 9 (6) ◽

pp. 479-492 ◽

Cited By ~ 49

Author(s):

P. Agarwal ◽

D. B. Searls

Keyword(s):

Drug Discovery ◽

Literature Mining

Download Full-text

A literature mining method to judge whether there are uncertainties in empirical-dependent antineoplastic drug distribution in specific clinical scenarios

10.1101/842401 ◽

2019 ◽

Author(s):

Xiaoyang Ji ◽

Zhendong Feng ◽

Qiangzu Zhang ◽

Zhonghai Zhang ◽

Yanhui Fan ◽

...

Keyword(s):

Clinical Practice ◽

Subjective Experience ◽

Linear Regression Analysis ◽

Drug Distribution ◽

Antineoplastic Drug ◽

Literature Mining ◽

Mining Method ◽

Clinical Scenarios ◽

Specific Cancer ◽

Cancer Types

AbstractCancer clinical practice guidelines recommend different treatment options for different cancer types and are mainly developed by clinicians. In theory, those recommendation schemes that are supported by scientific research should provide better efficacy for patients. However, in actual clinical practice: “Is the choice of a specific antineoplastic drug for a specific cancer supported by the results of molecular biology mechanisms or based on the subjective experience of the clinician?” Answering this question is of significant importance for guiding clinical practice, but there is currently no operational method to provide objective judgment in specific cases. This paper describes a literature mining method that collates information from specific antineoplastic drug-related literature to establish an antineoplastic drug-gene association matrix for global or specific cancer scenarios, and further establishes a standard model and scenario models. Based on the parameters of these models, we constructed a linear regression analysis method to evaluate whether the models in different scenarios deviated from a random distribution. Finally, we determined the possible efficacy of an antineoplastic drug in different cancer types, which was validated by the Genomics of Drug Sensitivity in Cancer (GDSC) database. Using our mining method, we tested 18 antineoplastic drugs in 16 cancer types. We found that cisplatin used in ovarian cancer was more efficacious and may benefit patients more than when used in breast cancer, which provides a new paradigm for rational knowledge-driven drug distribution patterns in clinical practice.

Download Full-text

Scientific literature mining for drug discovery: a case study on obesity

Drug Development Research ◽

10.1002/ddr.20416 ◽

2010 ◽

Vol 72 (2) ◽

pp. 201-208 ◽

Cited By ~ 4

Author(s):

Deepak K. Rajpal ◽

Vinod Kumar ◽

Pankaj Agarwal

Keyword(s):

Drug Discovery ◽

Scientific Literature ◽

Literature Mining

Download Full-text

Explaining Drug-Discovery Hypotheses Using Knowledge-Graph Patterns

10.1109/bigdata52589.2021.9672006 ◽

2021 ◽

Author(s):

Kara Schatz ◽

Cleber Melo-Filho ◽

Alexander Tropsha ◽

Rada Chirkova

Keyword(s):

Drug Discovery ◽

Knowledge Graph

Download Full-text

Biomedical Text Link Prediction for Drug Discovery: A Case Study with COVID-19

Pharmaceutics ◽

10.3390/pharmaceutics13060794 ◽

2021 ◽

Vol 13 (6) ◽

pp. 794

Author(s):

Kevin McCoy ◽

Sateesh Gudapati ◽

Lawrence He ◽

Elaina Horlander ◽

David Kartchner ◽

...

Keyword(s):

Drug Discovery ◽

Prediction Model ◽

Link Prediction ◽

Nucleoside Analogs ◽

Biomedical Literature ◽

Prediction Algorithm ◽

Knowledge Graph ◽

Recombinant Interferon ◽

Repurposed Drugs

Link prediction in artificial intelligence is used to identify missing links or derive future relationships that can occur in complex networks. A link prediction model was developed using the complex heterogeneous biomedical knowledge graph, SemNet, to predict missing links in biomedical literature for drug discovery. A web application visualized knowledge graph embeddings and link prediction results using TransE, CompleX, and RotatE based methods. The link prediction model achieved up to 0.44 hits@10 on the entity prediction tasks. The recent outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as COVID-19, served as a case study to demonstrate the efficacy of link prediction modeling for drug discovery. The link prediction algorithm guided identification and ranking of repurposed drug candidates for SARS-CoV-2 primarily by text mining biomedical literature from previous coronaviruses, including SARS and middle east respiratory syndrome (MERS). Repurposed drugs included potential primary SARS-CoV-2 treatment, adjunctive therapies, or therapeutics to treat side effects. The link prediction accuracy for nodes ranked highly for SARS coronavirus was 0.875 as calculated by human in the loop validation on existing COVID-19 specific data sets. Drug classes predicted as highly ranked include anti-inflammatory, nucleoside analogs, protease inhibitors, antimalarials, envelope proteins, and glycoproteins. Examples of highly ranked predicted links to SARS-CoV-2: human leukocyte interferon, recombinant interferon-gamma, cyclosporine, antiviral therapy, zidovudine, chloroquine, vaccination, methotrexate, artemisinin, alkaloids, glycyrrhizic acid, quinine, flavonoids, amprenavir, suramin, complement system proteins, fluoroquinolones, bone marrow transplantation, albuterol, ciprofloxacin, quinolone antibacterial agents, and hydroxymethylglutaryl-CoA reductase inhibitors. Approximately 40% of identified drugs were not previously connected to SARS, such as edetic acid or biotin. In summary, link prediction can effectively suggest repurposed drugs for emergent diseases.

Download Full-text